© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5034
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ány
    -0.28
    liest
    -0.27
    hana
    -0.26
    anj
    -0.26
    LOY
    -0.26
    licated
    -0.25
    renched
    -0.25
    ynos
    -0.25
     denen
    -0.25
     objs
    -0.24
    POSITIVE LOGITS
    pkt
    0.26
    ä¹Ĥ
    0.25
    /sys
    0.25
    -Q
    0.25
    -package
    0.24
    é¢Ĩ导
    0.24
     ÐłÐ¾Ñģ
    0.24
    æĪijåıªæĺ¯
    0.24
    表çݰ为
    0.24
    -A
    0.24
    Activations Density 0.388%

    No Known Activations

    This feature has no known activations.